5 19

Sirui Tao

FaceSoft

https://dylantao.github.io/

AI & ML interests

Computer Vision, Computer Graphics, 3D Learning, Multi-model Learning, Robotics, AI-aided Architecture & Design

Recent Activity

upvoted an article 16 days ago

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

liked a model 24 days ago

deepseek-ai/DeepSeek-V4-Pro

upvoted a collection 24 days ago

DeepSeek-V4

View all activity

Organizations

None yet

upvoted an article 16 days ago

Article

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

nvidia

•

Apr 28

• 60

liked a model 24 days ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 25 days ago • 5.89M • • 4.48k

upvoted a collection 24 days ago

DeepSeek-V4

Collection

4 items • Updated Apr 24 • 661

liked a model 9 months ago

tencent/HunyuanWorld-Voyager

Image-to-Video • Updated Oct 17, 2025 • 80 • 606

liked a model 11 months ago

microsoft/renderformer-v1.1-swin-large

Image-to-Image • Updated Dec 17, 2025 • 4.1k • 28

liked a model 12 months ago

nvidia/Cosmos-Transfer1-7B

Updated Nov 19, 2025 • 570 • 64

upvoted a collection 12 months ago

Cosmos-Transfer1

Collection

⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos-transfer25 • 5 items • Updated 2 days ago • 31

liked a dataset about 1 year ago

nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim

Updated Mar 5 • 306k • 227

liked a Space over 1 year ago

Diffusion Forcing Transformer

✨

Generate a video from any number of images

upvoted a paper over 1 year ago

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published Feb 3, 2025 • 69

liked a model over 1 year ago

nvidia/NVLM-D-72B

Image-Text-to-Text • 79B • Updated Jan 14, 2025 • 138k • 776

liked 2 Spaces almost 2 years ago

FLUX.1 [dev]

🖥

9.46k

Generate images from text prompts

FLUX.1 [Schnell]

🏎

5.07k

Generate images from text prompts with FLUX.1-schnell

liked a model almost 2 years ago

lllyasviel/sd-controlnet-canny

Image-to-Image • Updated May 1, 2023 • 25.6k • 247

liked a Space almost 2 years ago

CLIP Interrogator

🕵

2.97k

Generate detailed prompts from any image

updated a model about 2 years ago

FaceSoft/cbox_LoRA

Text-to-Image • Updated May 28, 2024 • 10 • 1

liked 3 models about 2 years ago

upvoted a paper over 2 years ago

Text-to-3D using Gaussian Splatting

Paper • 2309.16585 • Published Sep 28, 2023 • 33

Sirui Tao

AI & ML interests

Recent Activity

Organizations

FaceSoft's activity

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

Diffusion Forcing Transformer

FLUX.1 [dev]

FLUX.1 [Schnell]

CLIP Interrogator